Collaborating Authors

Google Brain co-founder teams with Foxconn to bring AI to factories


Consumers now experience AI mostly through image recognition to help categorize digital photographs and speech recognition that helps power digital voice assistants such as Apple Inc's Siri or But at a press briefing in San Francisco two days before Ng's In many factories, workers look over parts coming off an assembly line for defects. Ng showed a video in which a worker instead put a circuit board beneath a digital camera connected to a computer and the computer identified a defect in the part. Ng said that while typical computer vision systems might require thousands of sample images to become "trained,"'s

Google's cloudy image recognition is easily blinded, say boffins


Google's Cloud Vision API is easily blinded by the addition of a little noise to the images it analyses, say a trio of researchers from the Network Security Lab at the University of Washington, Seattle. Authors Hossein Hosseini, Baicen Xiao and Radha Poovendran have hit arXiv with a pre-press paper titled Google's Cloud Vision API Is Not Robust To Noise (PDF) that says "In essence, we found that by adding noise, we can always force the API to output wrong labels or to fail to detect any face or text within the image." The authors explain that if one can add different types of noise to an image, the Cloud Vision API will always incorrectly analyse the pictures presented to it. The image at the top of this story (or here for m.reg readers) shows the false results the API returned. It doesn;t need to be a lot of noise: the authors found an average of 14.25 per cent "impulse noise" got the job done.

Which company does the best job at image recognition? Microsoft, Amazon, Google, or IBM? ZDNet


Sometimes recognition software is excellent at correctly categorizing certain types of images but totally fails with others. Some image recognition engines prefer cats over dogs, and some are far more descriptive with their color knowledge. But which is the best overall? Perficient Digital's image recognition accuracy study looked at image recognition -- one of the hottest areas of machine learning. It looked at Amazon AWS Rekognition, Google Vision, IBM Watson, and Microsoft Azure Computer Vision to compare images.

AI, Apple and Google


In the last couple of years, magic started happening in AI. Techniques started working, or started working much better, and new techniques have appeared, especially around machine learning ('ML'), and when those were applied to some long-standing and important use cases we started getting dramatically better results. For example, the error rates for image recognition, speech recognition and natural language processing have collapsed to close to human rates, at least on some measurements. So you can say to your phone: 'show me pictures of my dog at the beach' and a speech recognition system turns the audio into text, natural language processing takes the text, works out that this is a photo query and hands it off to your photo app, and your photo app, which has used ML systems to tag your photos with'dog' and'beach', runs a database query and shows you the tagged images. There are really two things going on here - you're using voice to fill in a dialogue box for a query, and that dialogue box can run queries that might not have been possible before.

U.S. Air Force invests in Explainable-AI for unmanned aircraft


Software star-up, Z Advanced Computing, Inc. (ZAC), has received funding from the U.S. Air Force to incorporate the company's 3D image recognition technology into unmanned aerial vehicles (UAVs) and drones for aerial image and object recognition. ZAC's in-house image recognition software is based on Explainable-AI (XAI), where computer-generated image results can be understood by human experts. ZAC – based in Potomac, Maryland – is the first to demonstrate XAI, where various attributes and details of 3D objects can be recognized from any view or angle. "With our superior approach, complex 3D objects can be recognized from any direction, using only a small number of training samples," says Dr. Saied Tadayon, CTO of ZAC. "You cannot do this with the other techniques, such as deep Convolutional Neural Networks (CNNs), even with an extremely large number of training samples. That's basically hitting the limits of the CNNs," adds Dr. Bijan Tadayon, CEO of ZAC.